{"id":"W4366599818","doi":"10.17323/jle.2023.11045","title":"Automated Measures of Lexical Sophistication: Predicting Proficiency in an Integrated Academic Writing Task","year":2023,"lang":"en","type":"article","venue":"Journal of language and Education","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Waseda University","keywords":"Fluency; Sophistication; Computer science; Task (project management); Variance (accounting); Lexical diversity; Natural language processing; Language proficiency; Artificial intelligence; Second language writing; Psychology; Linguistics; Mathematics education; Vocabulary; Second language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002318454,0.0006559226,0.0003661619,0.002063061,0.0002366073,0.001654101,0.0004742999,0.0004720618,0.002009848],"category_scores_gemma":[0.02262061,0.000259138,0.0003690402,0.0009314714,0.0002742985,0.001116023,0.0008693041,0.0004583817,0.0009121108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002531409,"about_ca_system_score_gemma":0.0004502954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001114142,"about_ca_topic_score_gemma":0.00292997,"domain_scores_codex":[0.9984787,0.0006192955,0.0002275184,0.0003155098,0.000303109,0.00005582352],"domain_scores_gemma":[0.9771935,0.01401372,0.004981538,0.00098031,0.002128651,0.000702363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004906247,0.0006175024,0.8551677,0.0001768078,0.0002026118,0.0001395792,0.0009900917,0.003352529,0.00974805,0.0001705853,0.000800034,0.1281439],"study_design_scores_gemma":[0.00005368747,0.0007828832,0.9457747,0.00004806831,0.00007734012,0.0003596363,0.000396838,0.04264234,0.008351782,0.0006309082,0.000842034,0.00003978824],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920102,0.00005362896,0.006124661,0.00002496672,0.000004267581,0.00008633606,0.0004017568,0.0002154084,0.001078714],"genre_scores_gemma":[0.9886563,0.00004892588,0.00998224,0.00001257959,0.000006907453,0.0001321188,0.0005447122,0.00003248631,0.0005836329],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002318454,"threshold_uncertainty_score":0.01226133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04037119491325712,"score_gpt":0.3951687748602904,"score_spread":0.3547975799470333,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}